| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| ImagineFSL: Self-Supervised Pretraining Matters on Imagined Base Set for VLM-based Few-shot Learning | ✓ Link | 95 | ImagineFSL LoRA (16-shot) | 2025-06-11 |
| Adaptive Parameter Selection for Tuning Vision-Language Models | 94.45 | CLIP-AST (ViT-L/14) | 2025-06-11 | |
| BioMedVR: Confusion-Aware Mixture-of-Prompt Experts for Biomedical Visual Reprogramming | 93.9 | BioMedVR | 2026-06-23 | |
| Training-free Discriminative Patch Mining for Robust Few-Shot Recognition with CLIP | 87.14 | CDPS (OpenCLIP ViT-B/16, 16-shot) | 2026-09-08 | |
| BiCLIP: Domain Canonicalization via Structured Geometric Transformation | ✓ Link | 85.13 | BiCLIP (16-shot) | 2026-03-09 |
| LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP | ✓ Link | 80.53 | LP++ (16-shot) | 2024-04-02 |
| AdaBoosting Text Prompts for Vision-Language Models | ✓ Link | 66.9 | TPB (16-shot, OpenAI CLIP RN50) | 2026-07-01 |